Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

◉ Universal Intelligence: AI made simple.

LocalPlexity is a lite version of Perplexity aimed at 100% privacy and openness. Everything is done locally, in your browser, from searching the web to distilling a response for your question.

Rocus is an intelligent, AI-powered knowledge graph that automatically organizes your saved websites using local machine learning models. Built with Vue.js, D3.js, and WebGPU-accelerated AI, Rocus runs entirely in your browser with no servers, no cloud, complete privacy.

WhyAI – Inteligencia artificial generativa híbrida (offline y online) en navegador, privada y sin cuentas.

A privacy-first AI writing assistant running entirely in your browser using WebGPU and Llama-3. No server, no data leakage.

A React UI for Web LLM 💬

Omni-Dataset Immersive Navigator in eXtended Reality

IA Chat with web-llm library

End-to-end structured output for browser LLMs. Constrain Transformers.js/web-llm to valid JSON/SQL via GBNF grammars.

Use a LLM locally, with privacy and for free. Built using HTML, CSS and JavaScript.

🔒 Empower your writing with PrivAI, a local AI tool that ensures privacy while transforming text using advanced language models.

Web-LLM-based flavour of Merlin

Convert any website into markdown data for LLM

Use the online Gemini, Open AI or its compatible (v1/chat). Use offline with: @mlc-ai/web-llm, transformers.js-Whisper onnx, esearch-ocr. supports PWA to achieve offline conversation translation without restrictions.

PII Redactor for Gemini is a privacy first browser extension that runs a local, in-browser LLM between you and Gemini. It automatically identifies and redacts personally identifiable information, sensitive keywords, and custom data patterns before your prompt ever leaves your device.

Homelab device tracker with on-device AI classification

Quickly customize your GPT UI.

This application allows you to run large language models (LLMs) directly in your browser using Web-LLM.

use llm in browser without api calls, with webworker (multithreads in js)